摘要
在分析温度监测法、气体监测法、烟雾监测法、可见光图像监测法、红外图像监测法等矿井火灾监测方法原理和特点的基础上,提出了基于多参数融合的矿井火灾监测与趋势预测方法,得出以下结论:①热电偶测温法和半导体测温法具有准确率高、实时性强、能及时发现早期火灾等优点,但存在传感器用量大、维护工作量大等缺点;红外测温法具有监测范围广、传感器易于布置等优点,但传感器与被测物体间的遮挡物和煤尘等均会影响监测结果;光纤分布式测温法具有可监测多点温度、线缆用量小等优点,但存在光纤易损坏、安装复杂、维护困难等缺点。②气体监测法和烟雾监测法具有监测范围广、使用与维护方便等优点,但不能监测标志性气体浓度低、烟雾较小的早期火灾。③可见光图像监测法具有监测范围广、使用与维护方便、成本低等优点,但巷道灯、矿灯、车灯和红色衣物等干扰源及烟雾等均会影响监测效果,且不能监测没有火焰和烟雾较小的早期火灾。④红外图像监测法具有监测范围广、使用与维护方便等优点,但成本高,红外摄像机与被测物体间的遮挡物和煤尘等均会影响监测效果。⑤基于温度、烟雾、气体浓度、气味、风向、风速、风量、可见光图像和红外图像等多参数融合的矿井火灾监测与趋势预测方法不但能及时发现火灾,还可定位火源、预测火灾发展趋势。
Based on analysis of principle and characteristics of mine fire monitoring methods such as temperature monitoring method,gas monitoring method,smoke monitoring method,visible light image monitoring method and infrared image monitoring method,a mine fire monitoring and trend prediction method based on multi-parameter fusion was proposed. Conclusions were got as following:① Thermocouple temperature measurement method and semiconductor temperature measurement method have advantages of high accuracy,strong real-time performance and early detection of early fire,but there are disadvantages such as large sensor consumption and large maintenance workload;Infrared temperature measurement method has advantages of wide monitoring range and easy sensor arrangement,but shielding and coal dust between sensor and measured object will affect monitoring result;Fiber distributed temperature measurement method has advantages of multi-point temperature monitoring and small amount of cable consumption,but there are disadvantages such as easy damage,complicated installation and difficult maintenance of optical fiber.② Gas monitoring method and smoke monitoring method have advantages of wide monitoring range,convenient use and maintenance,but there are disadvantages such as cannot monitor early fire with low concentration of index gas and less smoke.③ Visible light image monitoring method has advantages of wide monitoring range,convenient use and maintenance,low cost,but interference sources such as roadway light,miner's lamp,vehicle lamp and red clothes and smoke will affect monitoring effect,and the method cannot monitor early fire with no flame and less smoke.④Infrared image monitoring method has advantages of wide monitoring range,convenient use and maintenance,but cost is high,and shielding and coal dust between infrared camera and measured object will affect monitoring effect.⑤ Mine fire monitoring and trend prediction method based on multiparameter fusion of temperature,smoke,gas concentration,odor,wind direction,wind speed,air volume,visible light image and infrared image can not only detect fire in time,but also locate fire source and predict fire development trend.
引文
[1]孙继平,钱晓红.煤矿重特大事故应急救援技术及装备[J].煤炭科学技术,2017,45(1):112-116.SUN Jiping,QIAN Xiaohong.Emergency rescue technology and equipment of mine extraordinary accidents[J].Coal Science and Technology,2017,45(1):112-116.
[2]孙继平.煤矿事故分析与煤矿大数据和物联网[J].工矿自动化,2015,41(3):1-5.SUN Jiping.Accident analysis and big data and Internet of things in coal mine[J].Industry and Mine Automation,2015,41(3):1-5.
[3]孙继平,钱晓红.煤矿事故与应急救援技术装备[J].工矿自动化,2016,42(10):1-5.SUN Jiping,QIAN Xiaohong.Coal mine accident and emergency rescue technology and equipment[J].Industry and Mine Automation,2016,42(10):1-5.
[4]雷忠青.矿井火灾预警技术研究[J].煤炭与化工,2015,38(10):148-149.LEI Zhongqing.Study on mine fire warning technology[J].Coal and Chemical Industry,2015,38(10):148-149.
[5]李军,张书林,龚仲强,等.基于多传感信息融合的输送带运输巷道火灾预警方法[J].煤矿机械,2017,38(10):132-135.LI Jun,ZHANG Shulin,GONG Zhongqiang,et al.Fire alarm method of conveying belt transportation roadway based on multi-sensor information fusion[J].Coal Mine Machinery,2017,38(10):132-135.
[6]贝伟仰,江虹.基于红外测温的无线温度监测系统的研究[J].计算机测量与控制,2011,19(10):2397-2400.BEI Weiyang,JIANG Hong.Study on temperature wireless monitoring system based on infrared technology[J].Computer Measurement&Control,2011,19(10):2397-2400.
[7]张箫剑.基于光纤测温技术的采空区煤温监测研究[D].淮南:安徽理工大学,2015.
[8]陈圣磊,梁建林,王恩慈.气体分析法早期预测预报煤炭自然发火技术研究[J].山东煤炭科技,2017(2):93-95.CHEN Shenglei,LIANG Jianlin,WANG Enci.Study on early prediction of coal spontaneous combustion by gas analysis[J].Shandong Coal Science and Technology,2017(2):93-95.
[9]齐斌.温度和烟雾监测及远程报警系统的设计与实现[D].成都:电子科技大学,2015.
[10]任慧,孙继平,刘晓阳.矿用电缆火灾图像识别方法[J].辽宁工程技术大学学报,2007,26(1):85-88.REN Hui,SUN Jiping,LIU Xiaoyang.Image recognition method of mine cable fires[J].Journal of Liaoning Technical University,2007,26(1):85-88.
[11]唐杰,周洋,杨萌,等.采用颜色混合模型和特征组合的视频烟雾检测[J].光电子·激光,2017,28(7):751-758.TANG Jie,ZHOU Yang,YANG Meng,et al.Asmoke detection algorithm using color mixture model and feature combination[J].Journal of Optoelectronics·Laser,2017,28(7):751-758.
[12]PREMAC E,VINSLEY S S,SURESH S.Multi feature analysis of smoke in YUV color space for early forest fire detection[J].Fire Technology,2016,52(5):1319-1342.
[13]王森,葛思擘,邹建华,等.结合颜色和外型特征的视频烟雾识别方法[J].计算机应用,2016,36(增刊2):168-170.WANG Sen,GE Sibo,ZOU Jianhua,et al.Video smoke detection based on color and shape features[J].Journal of Computer Applications,2016,36(S2):168-170.
[14]简文林.基于视频烟雾运动检测的火灾探测方法研究[D].南昌:南昌航空大学,2018.
[15]胡永才.基于低照度室内视频图像的烟雾检测算法研究[D].西安:西安科技大学,2017.
[16]FILONENKO A,HERNANDEZ D C,JO K H.Fast smoke detection for video surveillance using CUDA[J].IEEE Transactions on Industrial Informatics,2018,14(2):725-733.
[17]杜明本.基于视频监控的煤矿井下火灾识别算法研究[D].太原:太原科技大学,2016.
[18]胡云.基于红外热成像技术的矿井火灾识别系统研究[D].淮南:安徽理工大学,2016.